SuperAPI AI Directory
Partner with us中文AI newsFavorites

All AI tools

35,708 results · Page 898 of 992

Trellis 2

Other AI tools

Trellis 2 is an AI platform for 2D to 3D, powered by Trellis AI, supporting the rapid generation of 3D assets with texture details from images, photos, or text prompts. It provides workflows such as image-to-3D, photo-to-3D, and prompt-to-3D, primarily serving creators, studios, and product teams. The platform focuses on clearer shape, silhouette, and texture output, and supports exporting results to downstream processes such as DCC tools, game engines, and XR pipelines.

Read more

Trellis 2 AI

Other AI tools

Trellis 2 AI is an online AI 3D model generator that supports text-to-3D and image-to-3D, enabling rapid creation of product, character, scene, and concept models, with online preview and export. Users can generate models by entering a prompt or uploading a JPG, PNG, or WEBP image (up to 6MB). Free use is fast preview quality and costs 20 credits; paid high-quality generation costs 100 credits. Paid plans unlock Standard quality, offering better geometry and textures. The generation process uses credits, which are replenished according to the plan. Export formats include OBJ, FBX, GLB, and STL, and specific availability may vary. The tool is aimed at beginners and professionals, requires no 3D experience, and is suitable for scenarios such as product modeling, character drafts, game assets, e-commerce displays, and concept design. Currently, only a web version is available, with no dedicated mobile app, though it can be accessed via mobile browsers.

Read more

Trellis 3D AI

AI design

Trellis 3D AI is a next-generation AI 3D asset generation model developed by Microsoft that can generate high-quality 3D assets directly from text or image prompts. It uses a Structured LATent (SLAT) representation that can be decoded into multiple output formats such as Radiance Fields, 3D Gaussians, and meshes. The model scales up to 2 billion parameters and is trained on a diverse dataset of 500,000 objects, surpassing previous state-of-the-art solutions in detail, generality, and consistency. It supports local editing and variant creation and is suitable for professional workflows such as game development, 3D printing, architectural visualization, and product design. Installation requires a Linux system, Python 3.8+, an NVIDIA GPU with at least 16GB of VRAM, and the corresponding CUDA Toolkit, and deployment is completed by cloning the GitHub repository and running the setup.sh script.

Read more